Fast and Accurate Simulation of Particle Detectors Using Generative Adversarial Networks
Fast and Accurate Simulation of Particle Detectors Using Generative Adversarial Networks
复制标题
DOI：
10.1007/s41781-018-0015-y
复制
发表时间：
2018-05
影响因子：
--
通讯作者：
P. Musella;F. Pandolfi
中科院分区：
文献类型：
--
作者：
P. Musella;F. Pandolfi
由神经网络参数化的深度生成模型最近开始在自然图像建模中提供准确的结果。特别是，生成性对抗性网络为这一问题提供了一种无监督的解决方案。在这项工作中，我们将这种技术应用于粒子探测器对强子喷流响应的模拟。实验结果表明，深度神经网络在实现这一任务的保真度较传统算法提高几个数量级的同时，也能达到较高的保真度。
Deep generative models parametrised by neural networks have recently started to provide accurate results in modeling natural images. In particular, generative adversarial networks provide an unsupervised solution to this problem. In this work, we apply this kind of technique to the simulation of particle detector response to hadronic jets. We show that deep neural networks can achieve high fidelity in this task, while attaining a speed increase of several orders of magnitude with respect to traditional algorithms.